人工智能
Boosting(机器学习)
计算机科学
分割
模式识别(心理学)
计算机视觉
图像分割
分类器(UML)
特征(语言学)
阿达布思
作者
Heeji Yoon,Heeseong Shin,Eunbeen Hong,H. R. Choi,Hansang Cho,DaUn Jeong,Seungryong Kim
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-10-19
卷期号:: 20226-20236
被引量:9
标识
DOI:10.1109/iccv51701.2025.01881
摘要
Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to unreliable pseudo-label quality stemming from limited labeled data. While the Segment Anything Model (SAM) offers robust segmentation capabilities at various granularities, directly applying SAM to this task introduces challenges such as class-agnostic predictions and potential over-segmentation. To address these complexities, we carefully integrate SAM into the semi-supervised instance segmentation framework, developing a novel distillation method that effectively captures the precise localization capabilities of SAM without compromising semantic recognition. Furthermore, we incorporate pseudo-label refinement as well as a specialized data augmentation with the refined pseudo-labels, resulting in superior performance. We establish state-of-the-art performance, and provide comprehensive experiments and ablation studies to validate the effectiveness of our proposed approach.
科研通智能强力驱动
Strongly Powered by AbleSci AI